AI Safety Expert – English, Danish

This is a fully remote position, open to applicants in United States.

📋 Description

• Conduct red-team assessments on conversational AI models and agents through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Create high-quality human data by annotating errors, identifying vulnerabilities, and highlighting systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing procedures.

• Generate reproducible reports, datasets, and attack scenarios for clients.

• Identify vulnerabilities that automated testing might overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

• Enhance customer AI systems through adversarial testing methodologies.

• Collaborate with top researchers on initiatives focused on training and improving cutting-edge AI systems.

⛳️ Requirements

• Native proficiency in both English and Danish.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing.

• Capability to adversarially probe AI systems and challenge their limits.

• Proficient in utilizing structured frameworks, taxonomies, benchmarks, or playbooks.

• Ability to communicate risks effectively to both technical and non-technical audiences.

• Flexibility to adapt across various projects and client needs.

• Status as an independent contractor.

• Not eligible as an H1-B or STEM OPT candidate.

• Preferred qualifications include expertise in adversarial machine learning, cybersecurity, socio-technical risk, or creative probing.

• Experience in adversarial machine learning may encompass jailbreak datasets, prompt injections, RLHF/DPO attacks, or model extraction techniques.

• Cybersecurity experience may involve penetration testing, exploit development, or reverse engineering.

• Experience with socio-technical risks may include probing for harassment/disinformation, abuse analysis, or testing conversational AI systems.

• Creative probing experience might involve psychology, acting, or writing skills.

🏝️ Benefits

• Fully remote position.

• Flexible, self-managed schedule.

• Weekly payments processed via Stripe or Wise.

• Projects may be extended, shortened, or concluded early based on needs and performance evaluations.

• Participation in higher-sensitivity projects is optional.

• Clear content guidelines and access to wellness resources.

• Competitive compensation.

• Referral program providing up to $250 for each successful referral.

• Reasonable accommodations available upon request.

• Opportunity to collaborate with leading researchers.

• Chance to gain experience in human data-driven AI red teaming.